© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 127474
    Prev
    Next
    INDEX
    Explanations

    Vietnam and names

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     irrit
    0.42
    irrit
    0.40
     inviol
    0.39
    絕
    0.38
     destruir
    0.36
    衛星
    0.35
    ተ
    0.35
    ските
    0.35
    His
    0.34
    Philipp
    0.34
    POSITIVE LOGITS
     ډاونلوډ
    0.46
    喝
    0.44
     아이
    0.43
    自动
    0.43
     ഇപ്പോൾ
    0.43
     ніж
    0.42
     类
    0.41
     세율
    0.40
    kses
    0.40
    积分
    0.40
    Activations Density 0.002%

    No Known Activations